Research map / Label-efficient and robust learning / Recognition and long-tail
Metric-Based Auto-Instructor for Learning Mixed Data Representation
Songlei Jian, Liang Hu, Longbing Cao, Kai Lu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use MAI-F learned representation instead of plain encoding | k-means · 8 UCI datasets average | AMI: 0.1853±0.0707 -> 0.2467±0.0064 | Improved |
| use MAI-F representation instead of autoencoder | k-means · 8 UCI datasets average | AMI: 0.1944±0.0353 -> 0.2467±0.0064 | Improved |
| use MAI-F representation instead of plain encoding | DBSCAN · 8 UCI datasets average | AMI: 0.0451 -> 0.1845 | Improved |
| use MAI-F instead of autoencoder on Heart | k-means · Heart | AMI: 0.3302±0.0042 -> 0.2632±0.0000 | Hurt |
| use metric-based representation MAI-D instead of MAI-F (ablation) | MAI · 8 UCI datasets average (k-means) | AMI: 0.2467±0.0064 -> 0.2488±0.0010 | No clear effect |
| use MAI-F representation instead of autoencoder | representation separability · ACA | Calinski-Harabasz index: 124.37 -> 288.31 | Improved |
Closest papers by meaning
- MIC: Mining Interclass Characteristics for Improved Metric Learning (ICCV 2019 · similarity 0.86)
- It Takes Two to Tango: Mixup for Deep Metric Learning (ICLR 2022 · similarity 0.86)
- Divide and Conquer the Embedding Space for Metric Learning (CVPR 2019 · similarity 0.86)
- Improving Deep Metric Learning by Divide and Conquer (TPAMI 2021 · similarity 0.85)
- SLADE: A Self-Training Framework for Distance Metric Learning (CVPR 2021 · similarity 0.84)
- Sharing Matters for Generalization in Deep Metric Learning (TPAMI 2020 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
